Multilingual JobBERT for Cross-Lingual Job Title Matching

TL;DR

JobBERT-V3 is a multilingual contrastive learning model that improves cross-lingual job title matching across four languages, outperforming baselines and enabling broader labor market applications.

Contribution

It extends monolingual JobBERT-V2 to support four languages using synthetic translations and a large multilingual dataset, without task-specific supervision.

Findings

Outperforms strong multilingual baselines on TalentCLEF 2025

Achieves consistent performance in monolingual and cross-lingual tasks

Can rank relevant skills for job titles in multiple languages

Abstract

We introduce JobBERT-V3, a contrastive learning-based model for cross-lingual job title matching. Building on the state-of-the-art monolingual JobBERT-V2, our approach extends support to English, German, Spanish, and Chinese by leveraging synthetic translations and a balanced multilingual dataset of over 21 million job titles. The model retains the efficiency-focused architecture of its predecessor while enabling robust alignment across languages without requiring task-specific supervision. Extensive evaluations on the TalentCLEF 2025 benchmark demonstrate that JobBERT-V3 outperforms strong multilingual baselines and achieves consistent performance across both monolingual and cross-lingual settings. While not the primary focus, we also show that the model can be effectively used to rank relevant skills for a given job title, demonstrating its broader applicability in multilingual labor market intelligence. The model is publicly available: https://huggingface.co/TechWolf/JobBERT-v3.